{"id":"https://openalex.org/W4411346139","doi":"https://doi.org/10.1145/3679240.3734605","title":"Boosting the Performance of Deep Reinforcement Learning for Energy Management Systems using Behavior Cloning from Linear Programming Solutions","display_name":"Boosting the Performance of Deep Reinforcement Learning for Energy Management Systems using Behavior Cloning from Linear Programming Solutions","publication_year":2025,"publication_date":"2025-06-16","ids":{"openalex":"https://openalex.org/W4411346139","doi":"https://doi.org/10.1145/3679240.3734605"},"language":"en","primary_location":{"id":"doi:10.1145/3679240.3734605","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3679240.3734605","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3679240.3734605","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM International Conference on Future and Sustainable Energy Systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3679240.3734605","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Sheng Yin","orcid":"https://orcid.org/0009-0000-6059-0047"},"institutions":[{"id":"https://openalex.org/I2802623092","display_name":"Kempten University of Applied Sciences","ror":"https://ror.org/02m4p8096","country_code":"DE","type":"education","lineage":["https://openalex.org/I2802623092"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sheng Yin","raw_affiliation_strings":["Kempten University of Applied Sciences, Kempten, Germany"],"raw_orcid":"https://orcid.org/0009-0000-6059-0047","affiliations":[{"raw_affiliation_string":"Kempten University of Applied Sciences, Kempten, Germany","institution_ids":["https://openalex.org/I2802623092"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030903555","display_name":"Christoph Goebel","orcid":"https://orcid.org/0000-0002-5756-6983"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christoph Goebel","raw_affiliation_strings":["Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0002-5756-6983","affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035854523","display_name":"Holger C. Hesse","orcid":"https://orcid.org/0000-0002-6670-2684"},"institutions":[{"id":"https://openalex.org/I2802623092","display_name":"Kempten University of Applied Sciences","ror":"https://ror.org/02m4p8096","country_code":"DE","type":"education","lineage":["https://openalex.org/I2802623092"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Holger Hesse","raw_affiliation_strings":["Kempten University of Applied Sciences, Kempten, Germany"],"raw_orcid":"https://orcid.org/0000-0002-6670-2684","affiliations":[{"raw_affiliation_string":"Kempten University of Applied Sciences, Kempten, Germany","institution_ids":["https://openalex.org/I2802623092"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":20.7508,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.99529639,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"423","last_page":"435"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10917","display_name":"Smart Grid Security and Resilience","score":0.9817000031471252,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8160884380340576},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.7718918323516846},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6533042788505554},{"id":"https://openalex.org/keywords/cloning","display_name":"Cloning (programming)","score":0.6420251131057739},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.574398934841156},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5037474036216736},{"id":"https://openalex.org/keywords/linear-programming","display_name":"Linear programming","score":0.4983375072479248},{"id":"https://openalex.org/keywords/gradient-boosting","display_name":"Gradient boosting","score":0.49346935749053955},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47558796405792236},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.46137842535972595},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.33829569816589355},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1905958354473114},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13052165508270264},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12042149901390076},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07801893353462219},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.07511252164840698}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8160884380340576},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.7718918323516846},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6533042788505554},{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.6420251131057739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.574398934841156},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5037474036216736},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.4983375072479248},{"id":"https://openalex.org/C70153297","wikidata":"https://www.wikidata.org/wiki/Q5591907","display_name":"Gradient boosting","level":3,"score":0.49346935749053955},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47558796405792236},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.46137842535972595},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33829569816589355},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1905958354473114},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13052165508270264},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12042149901390076},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07801893353462219},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.07511252164840698},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3679240.3734605","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3679240.3734605","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3679240.3734605","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM International Conference on Future and Sustainable Energy Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3679240.3734605","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3679240.3734605","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3679240.3734605","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM International Conference on Future and Sustainable Energy Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.8799999952316284}],"awards":[],"funders":[{"id":"https://openalex.org/F4320330953","display_name":"Projekttr\u00e4ger J\u00fclich","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411346139.pdf","grobid_xml":"https://content.openalex.org/works/W4411346139.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W2207229987","https://openalex.org/W2773957237","https://openalex.org/W2801424816","https://openalex.org/W2961694391","https://openalex.org/W2962787969","https://openalex.org/W2976205474","https://openalex.org/W3090789943","https://openalex.org/W3108288031","https://openalex.org/W3130434474","https://openalex.org/W3201184503","https://openalex.org/W4210444794","https://openalex.org/W4233104126","https://openalex.org/W4281777895","https://openalex.org/W4323020891","https://openalex.org/W4366201163","https://openalex.org/W4388741412","https://openalex.org/W4400770903"],"related_works":["https://openalex.org/W2967733078","https://openalex.org/W3204430031","https://openalex.org/W3137904399","https://openalex.org/W4310492845","https://openalex.org/W2885778889","https://openalex.org/W4310224730","https://openalex.org/W4289703016","https://openalex.org/W2885516856","https://openalex.org/W3094138326","https://openalex.org/W1968832299"],"abstract_inverted_index":{"Energy":[0,7,212],"Management":[1,213],"Systems":[2],"(EMS)":[3],"for":[4,79],"controlling":[5],"Distributed":[6],"Resources":[8],"(DER)":[9],"like":[10],"batteries":[11],"in":[12,19,132,144,211],"buildings":[13],"play":[14],"an":[15,178],"increasingly":[16],"important":[17],"role":[18],"integrating":[20],"variable":[21],"renewable":[22],"energy.To":[23],"cope":[24],"with":[25],"their":[26],"increasing":[27],"complexity,":[28],"Deep":[29],"Reinforcement":[30],"Learning":[31,114],"(DRL)":[32],"has":[33],"been":[34],"suggested":[35],"as":[36,176],"data-driven":[37],"and":[38,59,136,186],"highly":[39],"flexible":[40],"control":[41],"method.However,":[42],"DRL":[43,77,161,210],"applied":[44],"to":[45,54,67,75,120,153,159,205],"EMS":[46],"still":[47],"suffers":[48],"from":[49,102],"relatively":[50],"poor":[51],"performance":[52],"compared":[53,158],"Model":[55],"Predictive":[56],"Control":[57],"(MPC)":[58],"requires":[60],"long":[61],"training":[62,134,165],"time":[63,84],"on":[64,89],"large":[65],"datasets":[66],"become":[68],"competitive.This":[69],"paper":[70],"presents":[71],"a":[72,110],"novel":[73],"approach":[74,150],"improve":[76],"controllers":[78],"solar":[80],"battery":[81],"systems":[82],"optimizing":[83],"of":[85,112,173,194,201,209],"energy":[86],"use":[87],"based":[88],"dynamic":[90],"prices":[91],"by":[92,122,167],"initializing":[93],"Proximal":[94],"Policy":[95],"Optimization":[96],"(PPO)":[97],"parameters":[98],"using":[99,123,140],"optimal":[100],"solutions":[101,175],"Linear":[103],"Programming":[104],"(LP).We":[105],"adapt":[106],"Behavior":[107],"Cloning":[108],"(BC),":[109],"form":[111],"Imitation":[113],"that":[115,148],"traditionally":[116],"transfers":[117],"human":[118,129],"expertise":[119],"robots,":[121],"mathematically":[124],"optimized":[125],"behaviors":[126],"rather":[127],"than":[128],"demonstrations,":[130],"resulting":[131],"reduced":[133],"steps":[135,166],"increased":[137],"performance.Experimental":[138],"results":[139],"actual":[141],"data":[142],"collected":[143],"industrial":[145],"microgrids":[146],"show":[147],"our":[149],"achieves":[151],"up":[152],"40%":[154],"higher":[155],"cost":[156],"savings":[157],"standard":[160],"models,":[162],"while":[163],"reducing":[164],"80%":[168],"requiring":[169],"just":[170],"4":[171],"weeks":[172],"LP":[174],"demonstrations.Using":[177],"extensive":[179],"sensitivity":[180],"analysis":[181],"across":[182],"various":[183],"load":[184],"profiles":[185],"system":[187],"sizing":[188],"parameters,":[189],"we":[190],"validate":[191],"the":[192,199,207],"robustness":[193],"these":[195],"improvements.Our":[196],"findings":[197],"highlight":[198],"potential":[200],"LP-based":[202],"parameter":[203],"initialization":[204],"accelerate":[206],"adoption":[208],"Systems.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}